Autor: |
Beig, R., Ehlers, J., Frisch, U., Hepp, K., Jaffe, R. L., Kippenhahn, R., Ojima, I., Weidenmüller, H. A., Wess, J., Zittartz, J., Beiglböck, W., Eisenächer, Monika, Clark, John W., Lindenau, Thomas, Ristig, Manfred L., Rost, Burkhard |
Zdroj: |
Scientific Applications of Neural Nets; 1999, p207-223, 17p |
Abstrakt: |
In the wake of the genome data flow, we need — more urgently than ever — accurate tools to predict protein structure. The problem of predicting protein structure from sequence remains fundamentally unsolved despite more than three decades of intensive research effort. However, the wealth of evolutionary information deposited in current databases enabled a significant improvement for methods predicting protein structure in 1D: secondary structure, transmembrane helices, and solvent accessibility. In particular, the combination of evolutionary information with neural networks has proved extremely successful. The new generation of prediction methods proved to be accurate and reliable enough to be useful in genome analysis, and in experimental structure determination. Moreover, the new generation of theoretical methods is increasingly influencing experiments in molecular biology. Neural networks have been applied to many pattern classification problems. Here, I review applications to the problem of predicting protein structure from protein sequence. Initially, methods were designed as a ‘quick and dirty' demonstration that artificial intelligence-based machines could solve real-life problems. At that stage, biologists typically reached higher levels of accuracy when using their expertise than computer scientists when using their machines. However, more thorough investigations introduced the information used by experts into neural network-based tools. Now, some tools are — on average — as accurate as the best experts, and experts using such tools often arrive at even more accurate predictions. Thus, several neural network-based methods have eventually contributed significantly to advancing the field of bio-informatics, and some are clearly influencing molecular biology. [ABSTRACT FROM AUTHOR] |
Databáze: |
Supplemental Index |
Externí odkaz: |
|